The goal of Coup RL is to create a reinforcement learning agent that learns to play the deception-based board game Coup. Can the agent learn an optimal strategy that outperforms human opponents? We also want to analyze the agent's learning to understand how the agent learned to lie and what strategies it uses. How can these ideas be applied to other problem spaces?
- Team Names & Project Abstract
- Project Description
- User Stories & Design Diagrams
- Project Tasks & Timeline
- Project Constraints
- Test Plan & Results
- Fall Presentation Slides & Video
- Spring Presentation Slides & Video
- Poster
- Training & Test Results
- Initial Self-Assessment
- Final Self-Assessment
- Professional Biography
- Budget
- Appendix & Hours Summary